Unverified50% confidenceFactExact time
GuardBreaker本质上是针对分析师工具的拒绝服务（DoS）攻击，伪装成安全触发器，并且因为模型安全训练做得好而奏效
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
GuardBreaker攻击：用核武器提示词瘫痪AI恶意软件分析
Related Entities
Cite This Claim
Stable URI
https://kongchang.com/claim/1000240API
curl https://kongchang.com/api/v1/knowledge/claims/1000240MCP
get_claim(id=1000240)